Meta-learning approach improves CNN architectures for concrete defect classification.
problem Challenging task of recognizing defects in concrete infrastructure.
method Two reinforcement learning based meta-learning approaches (MetaQNN and NAS) for finding suitable CNN architectures.
result Learned architectures have fewer parameters and better multi-target accuracy.
Concrete distribution properties examined on simplex.
problem Properties of Concrete distribution on simplex.
method Reflection and location-scale transformation of uniform distribution; explicit parameterization to Poincaré half-space.
result Fisher information and information metric are hyperbolic space; Fisher-Rao geodesic distance computed.
Concrete autoencoder selects key features for efficient data reconstruction.
problem Efficiently identifying and selecting important features for data reconstruction.
method Concrete selector layer with temperature-controlled selection during training, followed by reconstruction using a standard neural network.
result Concrete autoencoder selects a small subset of genes that can reconstruct the remaining gene expression levels, improving on existing methods.
Concrete distribution relaxes discrete variables for gradient-based optimization.
problem Gradient-based optimization of discrete random variables.
method Concrete distribution as a continuous relaxation of discrete variables, enabling reparameterization and gradient computation.
result Concrete distribution allows for low-variance biased gradients in discrete stochastic nodes.
Concrete proof that SO(n,1) is not a T-group.
problem Proving SO(n,1) is not a T-group.
method Constructed a concrete model for hyperbolic space and measure, proving hyperbolic distance equals measure up to a constant.
result Concrete proof that SO(n,1) is not a T-group.
Concrete example of 2-sphere with constant curvature 1 and closed geodesics.
problem Constructing a 2-sphere with constant curvature 1 and closed geodesics.
method Constructing a concrete example of a Finsler metric on the 2-sphere.
result A 2-sphere with constant Gauss curvature 1 and all geodesics closed.
Machine learning generates fragility curves for concrete bridges.
problem Estimating fragility curves for concrete bridges with uncertainty.
method Stripe-based approach using random forests.
result Fragility curves generated with reduced computational effort.
Concrete description of infinite order cork automorphism.
problem Describing the infinite order loose-cork automorphism.
method Concatenating the defining ribbon disk by an infinite order isotopy.
result Concrete description of the infinite order cork automorphism.
Proves a simplified version of Hitchin's theorem.
problem Constructing hyper-Kähler structures.
method Concrete variant of Hitchin's theorem.
result Applies to real manifolds without constructing hyper-Kähler structures.
Paper proposes a holistic optimization for civil structures considering uncertainties.
problem Designing civil structures requires integration of material and structural design.
method Holistic optimization combining concrete mixture design and structural simulations.
result Inverted workflow allows consideration of new mixtures and uncertainties.
Study provides concrete examples of knot slopes.
problem Finding explicit characterizing slopes for knots.
method Concrete examples for the (-2,3,7)-pretzel knot.
result Explicit characterizing slopes for the knot 12n242. Proposes an accuracy-preserving calibration method for DNNs.
problem Calibration of deep neural networks (DNNs) to measure prediction reliability.
method Uses Concrete distribution on the probability simplex to calibrate DNNs without accuracy loss.
result The proposed method outperforms previous methods in accuracy-preserving calibration tasks.
The present work constitutes the second part of a two-paper project that, in particular, deals with an in-depth study of effective techniques used in econometrics in order to make accurate forecasts in the concrete framework of one of the major economies of the most productive Italian area, namely the province of Veron…
We introduce non-acyclic PGLn(C)-torsion of a 3-manifold with toroidal boundary as an extension of J. Porti's PGL2(C)-torsion, and present an explicit formula of the PGLn(C)-torsion of a mapping torus for a surface with punctures, by using the higher Teichmüler theory due to V. Fock …
We define an extended Bloch group for an arbitrary field F, and show that this group is canonically isomorphic to K_3^ind(F) if F is a number field. This gives an explicit description of K_3^ind(F) in terms of generators and relations. We give a concrete formula for the regulator, and derive concrete symbol expressions…
A new method sparsifies neural networks using stochastic binary optimization.
problem Sparsifying neural networks to reduce computational cost and improve efficiency.
method Stochastic binary optimization with the Augment-Reinforce-Merge (ARM) estimator.
result ARM enables efficient network sparsification with comparable accuracy to baseline methods.
Classifies Hamiltonian and quasi-Hamiltonian manifolds with specific group actions.
problem Classifying specific types of manifolds under group actions.
method General classification of multiplicity free manifolds, focusing on rank one.
result Obtained numerous new concrete examples of quasi-Hamiltonian manifolds.
Improved CAEs reduce training time and enhance generalization.
problem Stability issues in Concrete Autoencoders (CAEs) for feature selection.
method Indirectly Parameterized Concrete Autoencoders (IP-CAEs) learn parameters of Gumbel-Softmax distributions.
result IP-CAEs achieve significant improvements in generalization and training time.
The interplay between the Hamilton-Jacobi theory of orthogonal separation of variables and the theory of group actions is investigated based on concrete examples.
We show that Scharlemann-Thompson untelescoping of Heegaard splittings is finer than Casson-Gordon's by giving concrete examples.
The book explores stochastic areas and heat kernels on manifolds.
problem Understanding stochastic area functionals and heat kernels on manifolds.
method Study of Brownian motions and heat kernels on Lie groups and Riemannian manifolds.
result Rich interactions between stochastic calculus, geometry, and random matrices.
We calculate the volumes of the hyperbolic twist knot cone-manifolds using the Schläfli formula. Even though general ideas for calculating the volumes of cone-manifolds are around, since there is no concrete calculation written, we present here the concrete calculations. We express the length of the singular locus in t…
This is a short survey on finite-volume hyperbolic four-manifolds. We describe some general theorems and focus on the concrete examples that we found in the literature. The paper contains no new result.
Proposes a few-shot learning method for feature selection without labeled data.
problem Feature selection in unlabeled data with limited instances.
method Uses Concrete random variables and permutation-invariant neural networks to select features from multiple source tasks.
result Outperforms existing methods in feature selection performance.
Upper bounds on neural network complexity for PDE solutions.
problem Approximating solutions of parametric PDEs without knowing their exact form.
method Using low-dimensionality of solution manifolds and a small reduced basis.
result Neural networks can approximate PDE solutions with sizes dependent only on the reduced basis.
The paper describes Hermitian non-Kähler structures on complex flag manifolds.
problem Understanding Hermitian non-Kähler structures on products of principal S¹-bundles.
method Using representation theory of complex simple Lie algebras and Cartan-Ehresmann connections.
result Explicit description of Hermitian non-Kähler manifolds and families of complex structures.
Deep k-means learns clustering and features from unlabeled data.
problem Clustering and feature learning from unlabeled data.
method Gradient-estimator for non-differentiable k-means objective via Gumbel-Softmax reparameterisation.
result Concrete k-means model optimised for canonical k-means objective, end-to-end trainable.
We show a concise extension of the monotone stability approach to backward stochastic differential equations (BSDEs) that are jointly driven by a Brownian motion and a random measure for jumps, which could be of infinite activity with a non-deterministic and time inhomogeneous compensator. The BSDE generator function c…
This work is the first part of a project dealing with an in-depth study of effective techniques used in econometrics in order to make accurate forecasts in the concrete framework of one of the major economies of the most productive Italian area, namely the province of Verona. In particular, we develop an approach mainl…
A flat Klein bottle is visualized using origami.
problem Visualizing a Klein bottle's flatness and topology.
method Curved-crease origami with inelastic film.
result The sculpture illustrates both flatness and non-orientability.
New algorithm for non-Markovian optimal stopping problems using Brownian motion.
problem Optimal stopping time problems for non-Markovian state processes.
method Longstaff-Schwartz-type algorithm based on statistical learning theory.
result Error estimates for approximation architecture spaces with finite Vapnik-Chervonenkis dimension.
We continue the study of blow-ups in generalized complex geometry with the blow-up theory for generalized Kähler manifolds. The natural candidates for submanifolds to be blown-up are those which are generalized Poisson for one of the two generalized complex structures and can be blown up in a generalized complex manner…
The aim of this paper is to present the stochastic Poisson equations associated to Lie algebroids. The stochastic Poisson equations associated to a refinement of a concrete principal bundle are determined.
This study assesses model influence on RL algorithm performance.
problem Unclear contribution of model-based RL algorithms to recent progress.
method Established a set of models for comparison, including NNs, BNNs, GPs, and ensembles.
result Concrete Dropout NN shows superior performance across benchmark tasks.
The Klein-Grifone approach to global Finsler geometry is adopted. The nullity distributions of the three curvature tensors of Cartan connection are investigated. Nullity distributions concerning certain relevant special Finsler spaces are considered. Concrete examples are given whenever the situation needs.
Switching linear dynamics improves model-based reinforcement learning and system identification.
problem Complex and nonlinear systems can be approximated by linear dynamical systems.
method Bayesian inference, Variational Autoencoders, Concrete relaxations.
result Improved accuracy in learning dynamics from partial and high-dimensional observations.
We give a topological and geometrical description of focus-focus singularities of integrable Hamiltonian systems. In particular, we explain why the monodromy around these singularities is non-trivial, a result obtained before by J.J. Duistermaat and others for some concrete systems.
Paper presents ML approaches for faster brittle fracture modeling.
problem Faster modeling of brittle fracture in concrete.
method Machine learning algorithms combined with physics-based assumptions.
result ML models are orders of magnitude faster than high-fidelity models.
DisCoPyro combines category theory with machine learning for program learning.
problem Applying category theory to machine learning tasks.
method Introducing DisCoPyro, a framework combining categorical structures with amortized variational inference.
result DisCoPyro can be applied in program learning for variational autoencoders and potentially contributes to AGI.
We consider ruled surfaces in the three-dimensional Euclidean space and some geometrically distinguished families of curves on them whose normal curvature has a concrete form. The aim of this paper is to find and classify all ruled surfaces with the mentioned property
Solves Dirac equation coupled to vector bundles.
problem Yang-Mills equations and vector bundles on Riemann surfaces.
method Analyzes coupled Dirac operators.
result Provides concrete solutions to the Dirac equation.
We concretely construct a 2-categorically extended TQFT that extends the Reshetikhin-Turaev TQFT to cobordisms with corners. The source category will be a well chosen 2-category of decorated cobordisms with corners and the target bicategory will be the Kapranov-Voevodsky 2-vector spaces.
We investigate the curvature properties of a two-parameter family of Hermitian structures on the product of two Sasakian manifolds, as well as intermediate relations. We give a necessary and sufficient condition for a Hermitian structure belonging to the family to be Einstein and provide concrete examples.
A "Chen space" is a set X equipped with a collection of "plots" - maps from convex sets to X - satisfying three simple axioms. While an individual Chen space can be much worse than a smooth manifold, the category of all Chen spaces is much better behaved than the category of smooth manifolds. For example, any subspace …
Geometric obstructions prevent gravity in high dimensions.
problem Obstacles to realizing gravity in various geometries.
method Analyzing the tetradic Einstein-Hilbert-Palatini action in different geometric settings.
result Gravity is only meaningful in Lorentzian geometry for dimensions n≥4. Framework improves GCNs for graphless and adversarial settings.
problem Improving GCNs without graph data and making them robust to adversarial attacks.
method Joint probabilistic model with variational inference and Concrete distributions.
result Framework outperforms state-of-the-art algorithms on semi-supervised classification.
Paper transforms torse-forming vector fields into simpler forms.
problem Generalizing vector fields and their transformations.
method Present techniques to transform torse-forming vector fields into simpler cases.
result Concrete examples of transformations are provided.
We study parallel surfaces and dual surfaces of cuspidal edges. We give concrete forms of principal curvature and principal direction for cuspidal edges. Moreover, we define ridge points for cuspidal edges by using those. We clarify relations between singularities of parallel and dual surfaces and differential geometri…